How do you analyse data over time using a time series, moving averages and a trend line, allowing for seasonal variation?
Plot and interpret a time series, calculate moving averages to smooth the data, plot and use a trend line, identify seasonal variation, and use the trend to make predictions.
A CCEA GCSE Statistics answer on time series: plotting a time series, calculating moving averages to smooth fluctuations, plotting a trend line, identifying seasonal variation, and using the trend to predict.
Reviewed by: AI editorial process; not yet individually human-reviewed
Have a quick question? Jump to the Q&A page
Jump to a section
What this dot point is asking
A time series is data recorded at regular intervals over time, such as quarterly sales or monthly rainfall. CCEA expects you to plot a time series, calculate moving averages to smooth out short-term and seasonal variation, plot a trend line, identify seasonal variation, and use the trend to predict. The moving-average calculation is the central skill, and choosing the right number of points to match the cycle is a frequent exam point.
Plotting and reading a time series
A time-series graph plots the variable on the vertical axis against time on the horizontal axis, with the points joined in order.
The raw graph is hard to read because the seasonal pattern hides the trend, so we smooth it with moving averages.
Moving averages
A moving average smooths the data by repeatedly averaging a fixed number of consecutive values.
The trend line and predictions
Plotting the moving averages and drawing a straight trend line through them shows the trend clearly. Extending the trend line predicts a future value, but only as an estimate, because the trend may not continue. A prediction is more accurate near the data and less reliable the further ahead it goes (this is extrapolation again).
A fuller prediction adds the seasonal variation back on: estimate how far a particular season usually sits above or below the trend, then add that to the trend value for that season. For example, if summer is typically 5 above the trend, a summer prediction is the trend value plus 5. The seasonal effect for a season is found by comparing the actual values with the trend (moving average) at that season and averaging the differences, so each season has its own typical adjustment that you reuse when forecasting.
Why this matters
Time-series analysis is how businesses and governments track sales, unemployment, prices and weather, and it is central to the Unit 2 case study on real Northern Ireland data over time. Moving averages are a reliable calculation, and understanding why the cycle length sets the number of points is exactly the reasoning CCEA rewards. Separating trend from seasonal variation is a genuine analytical skill used in real forecasting.
Exam-style practice questions
Practice questions written in the style of CCEA exam questions on this dot point, with worked answer explainers. The year tag is the paper they imitate, not the source.
CCEA-style4 marksQuarterly sales (in thousands) are 12, 18, 16, 10, 14, 20. Calculate the four-point moving averages.Show worked answer →
A four-point moving average averages four consecutive values, then moves on by one.
First: .
Second: .
Third: .
The moving averages are . Four marks (method and three correct values). They smooth out the quarterly ups and downs, revealing a gently rising trend. Use a four-point average for quarterly data because there are four seasons in the cycle.
CCEA-style3 marksExplain why moving averages are used on a time series, and how the number of points in the moving average is chosen.Show worked answer →
Moving averages are used to smooth out short-term fluctuations and seasonal variation so that the underlying trend becomes clear. One mark for smoothing, one for revealing the trend.
The number of points matches the length of the cycle: a four-point moving average for quarterly (four-season) data, a seven-point for daily data over a week, a twelve-point for monthly data over a year. One mark. Matching the cycle length removes the repeating seasonal pattern.
Related dot points
- Calculate and interpret simple index numbers, understand the Retail Prices Index and Consumer Prices Index, find a weighted index number, and use a chain base to compare year-on-year change.
A CCEA GCSE Statistics answer on index numbers: simple price and quantity index numbers, the base year, the Retail Prices Index and Consumer Prices Index, weighted index numbers, and the chain base method.
- Construct and interpret frequency tables, two-way tables, pictograms, bar charts (including composite and comparative), pie charts and stem-and-leaf diagrams, choosing the correct display for the type of data.
A CCEA GCSE Statistics answer on tabulating and displaying data: frequency and two-way tables, pictograms, bar charts including composite and comparative bar charts, pie charts and stem-and-leaf diagrams, and choosing the right display.
- Calculate the mean, median and mode, find a weighted mean and the mean from a frequency or grouped frequency table, identify the modal class, and choose the most appropriate average for the data.
A CCEA GCSE Statistics answer on measures of central tendency: the mean, median and mode, the weighted mean, the mean from frequency and grouped tables, the modal class, and choosing the most appropriate average.
- Draw and interpret scatter diagrams, describe correlation, use a line of best fit to estimate values (interpolation and extrapolation), understand that correlation does not imply causation, and calculate and interpret Spearman's rank correlation coefficient.
A CCEA GCSE Statistics answer on bivariate data: scatter diagrams, types and strength of correlation, the line of best fit, interpolation and extrapolation, correlation versus causation, and Spearman's rank correlation coefficient.
- Construct and interpret frequency polygons, histograms with equal and unequal class widths using frequency density, and cumulative frequency curves, and read the median and quartiles from a cumulative frequency curve.
A CCEA GCSE Statistics answer on representing grouped continuous data: frequency polygons, histograms with frequency density and unequal class widths, cumulative frequency tables and curves, and reading the median and quartiles.
Sources & how we know this
- CCEA GCSE Statistics (2017) specification (2260) — CCEA (2017)